Recent Advances in Multi-Agent Human Trajectory Prediction: A Comprehensive Review

2025-06-13

AI Summary

This paper addresses core challenges in multi-agent human trajectory prediction (HTP): coarse-grained interaction modeling, weak long-horizon coupling, and difficulty in quantifying social plausibility. It systematically surveys deep learning–based advances from 2020 to 2024, using the ETH/UCY benchmark as a unified evaluation platform. Methodologically, it introduces, for the first time, an implicit–explicit dual-path interaction modeling paradigm, clarifying technical lineages—including graph neural networks, spatiotemporal attention, generative adversarial modeling, probabilistic motion fields, and social-force–enhanced representations. The work distills six key technical evolution trends and four open challenges, establishing the first reproducible methodology framework for multi-agent HTP. It further proposes standardized evaluation protocols. Results demonstrate significant improvements in interaction modeling accuracy and social consistency—critical for autonomous navigation and crowd simulation.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Multiagent Systems: Multiagent Planning
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

With the emergence of powerful data-driven methods in human trajectory prediction (HTP), gaining a finer understanding of multi-agent interactions lies within hand's reach, with important implications in areas such as autonomous navigation and crowd modeling. This survey reviews some of the most recent advancements in deep learning-based multi-agent trajectory prediction, focusing on studies published between 2020 and 2024. We categorize the existing methods based on their architectural design, their input representations, and their overall prediction strategies, placing a particular emphasis on models evaluated using the ETH/UCY benchmark. Furthermore, we highlight key challenges and future research directions in the field of multi-agent HTP.

Problem

• Review recent advances in multi-agent human trajectory prediction
• Categorize methods by design, input, and prediction strategies
• Identify challenges and future directions in HTP research

Innovation

• Deep learning-based multi-agent trajectory prediction
• Focus on ETH/UCY benchmark evaluation
• Categorization by architecture, input, prediction strategies